21 Commits

Author	SHA1	Message	Date
LordMathis	f17debc244	Implement getOutputSize and getInputSize for seq layers	2024-04-22 20:31:58 +02:00
LordMathis	a32c737785	Allocate activation on heap	2024-04-22 18:59:16 +02:00
LordMathis	d08567a563	Fix weigh bias parsing and better error logging	2024-04-20 18:36:53 +02:00
LordMathis	9fb9d7e8e1	Implement getting layer, weights and biases	2024-04-16 19:09:41 +02:00
LordMathis	90fb104dae	Implement output layer	2024-03-21 23:07:46 +01:00
LordMathis	b6c4b7d2ae	Refactor layers	2024-03-19 21:35:05 +01:00
LordMathis	d9c6c663c8	Rename ILayer to WeightedLayer	2024-03-18 20:36:52 +01:00
LordMathis	42d646750b	Abstract activation and implement softmax	2024-03-17 18:37:15 +01:00
LordMathis	0c22fac64e	Add toplevel CUDANet namespace	2024-03-17 16:08:53 +01:00
LordMathis	dc86cddeb7	Use tiling shmem for mat vec mul kernel	2024-03-15 23:33:09 +01:00
LordMathis	88f7fff217	Add prefix to guards	2024-03-13 22:23:23 +01:00
LordMathis	7157a27e56	Add documentation comments	2024-03-12 21:50:06 +01:00
LordMathis	9d91896f13	Change forward function to return output pointer	2024-03-12 20:50:49 +01:00
LordMathis	d2ab78fbc7	Add Kernels namespace	2024-03-11 21:04:23 +01:00
LordMathis	e0178e2d5c	Cleanup and refactor	2024-03-11 20:39:44 +01:00
LordMathis	f4257afd5a	Remove cublas dependency	2024-03-05 18:41:35 +01:00
LordMathis	cfc5c46d5e	Initialize conv2d layer	2024-03-04 22:16:03 +01:00
LordMathis	f37320594a	Add activations enum	2024-03-03 15:24:54 +01:00
LordMathis	48ba09b28d	Format source code using clang-format	2024-02-27 18:52:12 +01:00
LordMathis	5e1e0ed1d1	Initial activations implementation	2024-02-27 00:24:57 +01:00
LordMathis	6e99525ad0	Rename hheader files to .cuh	2024-02-26 19:53:46 +01:00